INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĸļ

-0.76

inence

-0.72

rir

-0.69

qua

-0.69

spir

-0.68

Italy

-0.65

obyl

-0.64

atri

-0.64

arium

-0.63

ibaba

-0.62

POSITIVE LOGITS

 solicitation

0.76

EGIN

0.67

 suspicions

0.67

 collusion

0.66

 loophole

0.66

 sightings

0.66

 Myster

0.65

Anonymous

0.64

 loopholes

0.64

ocent

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.